Alibaba's performant long context models for agentic and coding tasks.
348.9K Pulls 9 Tags Updated 3 weeks ago
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
7.8M Pulls 56 Tags Updated 1 month ago
2,936 Pulls 4 Tags Updated 4 months ago
Unsloth Dynamic 2.0 Quants achieves 1M tokens & superior accuracy & SOTA quantization performance. Select UD-IQ3_XXS for 16GB VRAM, UD-Q4_K_XL for 24GB VRAM, or UD-Q5_K_XL/UD-Q6_K_XL for 32GB VRAM.
2,240 Pulls 5 Tags Updated 3 weeks ago
Qwen3-Coder featuring the following key enhancements: Significant Performance, Long-context Capabilities, Agentic Coding.
1,936 Pulls 9 Tags Updated 1 month ago
1,891 Pulls 2 Tags Updated 2 months ago
Alibaba's performant long context models for agentic and coding tasks — quantized and optimized in GGUF format by Unsloth for fast local inference on consumer devices.
1,417 Pulls 1 Tag Updated 1 month ago
The most powerful open-source coding AI - 480B parameters with Mixture of Experts architecture for exceptional code generation and understanding.
1,172 Pulls 6 Tags Updated 1 month ago
https://huggingface.co/burtenshaw/Qwen3-30B-A3B-python-coder
829 Pulls 2 Tags Updated 4 months ago
Qwen3-Coder is available in multiple sizes. Today, we’re excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency ........
603 Pulls 1 Tag Updated 3 weeks ago
This is not the ablation version. Qwen3-Coder featuring the following key enhancements: Significant Performance, Long-context Capabilities, Agentic Coding.
464 Pulls 4 Tags Updated 1 month ago
Alibaba's Qwen3-Coder-30B 4bit with 1M token context. Enhanced tool calling for agentic coding tasks
422 Pulls 1 Tag Updated 1 month ago
Alibaba's Qwen3-Coder-30B 4bit with 256k token context. Enhanced tool calling for agentic coding tasks
341 Pulls 1 Tag Updated 1 month ago
model Qwen3-Coder-30B-A3B-Instruct-Q5_K_M
340 Pulls 1 Tag Updated 1 month ago
qwen3-coder with tools calling, context 58k to match full memory 31GB on RTX5090
302 Pulls 1 Tag Updated 3 weeks ago
transformed from qwen3-coder-30b-a3b-instruct
241 Pulls 1 Tag Updated 1 month ago
Weights, parameters and templates are taken from unsloth. Tools and MCP servers work correctly. Tested on Continue for VS Code
181 Pulls 4 Tags Updated 1 month ago
178 Pulls 1 Tag Updated 2 months ago
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud. (quantized UD-Q4_K_XL + 1M context)
84 Pulls 3 Tags Updated 5 days ago
62 Pulls 1 Tag Updated 1 month ago